\( \newcommand{\bm}[1]{\boldsymbol{#1}} \newcommand{\textm}[1]{\textsf{#1}} \def\T{{\mkern-2mu\raise-1mu\mathsf{T}}} \newcommand{\R}{\mathbb{R}} % real numbers \newcommand{\E}{{\rm I\kern-.2em E}} \newcommand{\w}{\bm{w}} % bold w \newcommand{\bmu}{\bm{\mu}} % bold mu \newcommand{\bSigma}{\bm{\Sigma}} % bold mu \newcommand{\bigO}{O} %\mathcal{O} \renewcommand{\d}[1]{\operatorname{d}\!{#1}} \)

Chapter 9 High-Order Portfolios

“The study of economics does not seem to require any specialised gifts of an unusually high order.”

— John Maynard Keynes

Markowitz’s mean–variance portfolio optimizes a trade-off between expected return and risk measured by the variance. However, since financial data is not Gaussian distributed, due to asymmetry and heavy tails in the distribution, it would be reasonable to also incorporate higher-order moments.

Unfortunately, designing a portfolio based on the first four moments (i.e., mean, variance, skewness, and kurtosis) brings at least two critical difficulties:

  • The dimensionality of the higher-order moments grows as \(N^4\), where \(N\) is the number of assets, with implications in the complexity of the moment computation, memory storage, and algorithmic manipulation.

  • The portfolio formulations are nonconvex, further complicating the design and optimization.

High-order portfolios were formulated over half a century ago, but only recently they have become a practical reality for large number of assets in the order of hundreds or even thousands.

This material will be published by Cambridge University Press as Portfolio Optimization: Theory and Application by Daniel P. Palomar. This pre-publication version is free to view and download for personal use only; not for re-distribution, re-sale, or use in derivative works. © Daniel P. Palomar 2024.